Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers—8× deeper than VGG nets [40] but still having lower complexity. An ensemble of these residual nets achieves 3.57% error on the ImageNet test set. This result won the 1st place on the ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100 and 1000 layers. The depth of representations is of central importance for many visual recognition tasks. Solely due to our extremely deep representations, we obtain a 28% relative improvement on the COCO object detection dataset. Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions1, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.

/pdf/deep-residual-learning-for-image-recognition-b75jg61qrq.pdf

Deep Residual Learning for Image Recognition

In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision.

Very Deep Convolutional Networks for Large-Scale Image Recognition

The explosion of image data on the Internet has the potential to foster more sophisticated and robust models and algorithms to index, retrieve, organize and interact with images and multimedia data. But exactly how such data can be harnessed and organized remains a critical problem. We introduce here a new database called “ImageNet”, a large-scale ontology of images built upon the backbone of the WordNet structure. ImageNet aims to populate the majority of the 80,000 synsets of WordNet with an average of 500-1000 clean and full resolution images. This will result in tens of millions of annotated images organized by the semantic hierarchy of WordNet. This paper offers a detailed analysis of ImageNet in its current state: 12 subtrees with 5247 synsets and 3.2 million images in total. We show that ImageNet is much larger in scale and diversity and much more accurate than the current image datasets. Constructing such a large-scale database is a challenging task. We describe the data collection scheme with Amazon Mechanical Turk. Lastly, we illustrate the usefulness of ImageNet through three simple applications in object recognition, image classification and automatic object clustering. We hope that the scale, accuracy, diversity and hierarchical structure of ImageNet can offer unparalleled opportunities to researchers in the computer vision community and beyond.

/pdf/imagenet-a-large-scale-hierarchical-image-database-1e8f663s1h.pdf

ImageNet: A large-scale hierarchical image database

There is large consent that successful training of deep networks requires many thousand annotated training samples. In this paper, we present a network and training strategy that relies on the strong use of data augmentation to use the available annotated samples more efficiently. The architecture consists of a contracting path to capture context and a symmetric expanding path that enables precise localization. We show that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks. Using the same network trained on transmitted light microscopy images (phase contrast and DIC) we won the ISBI cell tracking challenge 2015 in these categories by a large margin. Moreover, the network is fast. Segmentation of a 512x512 image takes less than a second on a recent GPU. The full implementation (based on Caffe) and the trained networks are available at http://lmb.informatik.uni-freiburg.de/people/ronneber/u-net .

/pdf/u-net-convolutional-networks-for-biomedical-image-2xoyjzggxv.pdf

U-Net: Convolutional Networks for Biomedical Image Segmentation

Matching people based on their imaged face is hard because of the well known problems of illumination, pose, size and expression variation. Indeed these variations can exceed those due to identity. Fortunately, videos of people have the happy benefit of containing multiple exemplars of each person in a form that can easily be associated automatically using straightforward visual tracking. We describe progress in harnessing these multiple exemplars in order to retrieve humans automatically in videos, given a query face in a shot. There are three areas of interest: (i) the matching of sets of exemplars provided by “tubes” of the spatial-temporal volume; (ii) the description of the face using a spatial orientation field; and, (iii) the structuring of the problem so that retrieval is immediate at run time.

The result is a person retrieval system, able to retrieve a ranked list of shots containing a particular person in the manner of Google. The method has been implemented and tested on two feature length movies.

/pdf/person-spotting-video-shot-retrieval-for-face-sets-uo1t0ht5s4.pdf

Person spotting: video shot retrieval for face sets

We investigate the problem of automatically labelling faces of characters in TV or movie material with their names, using only weak supervision from automatically-aligned subtitle and script text. Our previous work (Everingham et al. [8]) demonstrated promising results on the task, but the coverage of the method (proportion of video labelled) and generalization was limited by a restriction to frontal faces and nearest neighbour classification. In this paper we build on that method, extending the coverage greatly by the detection and recognition of characters in profile views. In addition, we make the following contributions: (i) seamless tracking, integration and recognition of profile and frontal detections, and (ii) a character specific multiple kernel classifier which is able to learn the features best able to discriminate between the characters. We report results on seven episodes of the TV series "Buffy the Vampire Slayer", demonstrating significantly increased coverage and performance with respect to previous methods on this material.

/pdf/who-are-you-learning-person-specific-classifiers-from-video-4r0qoumn5a.pdf

“Who are you?” - Learning person specific classifiers from video

This paper proposes and compares two novel schemes for near duplicate image and video-shot detection. The first approach is based on global hierarchical colour histograms, using Locality Sensitive Hashing for fast retrieval. The second approach uses local feature descriptors (SIFT) and for retrieval exploits techniques used in the information retrieval community to compute approximate set intersections between documents using a min-Hash algorithm.The requirements for near-duplicate images vary according to the application, and we address two types of near duplicate definition: (i) being perceptually identical (e.g. up to noise, discretization effects, small photometric distortions etc); and (ii) being images of the same 3D scene (so allowing for viewpoint changes and partial occlusion). We define two shots to be near-duplicates if they share a large percentage of near-duplicate frames.We focus primarily on scalability to very large image and video databases, where fast query processing is necessary. Both methods are designed so that only a small amount of data need be stored for each image. In the case of near-duplicate shot detection it is shown that a weak approximation to histogram matching, consuming substantially less storage, is sufficient for good results. We demonstrate our methods on the TRECVID 2006 data set which contains approximately 165 hours of video (about 17.8M frames with 146K key frames), and also on feature films and pop videos.

/pdf/scalable-near-identical-image-and-shot-detection-4x7b7xxolg.pdf

Scalable near identical image and shot detection

A new method is described for automatically reconstructing 3D planar faces from multiple images of a scene. The novelty of the approach lies in the use of inter-image homographies to validate and best estimate the plane, and in the minimal initialization requirements-only a single 3D line with a textured neighbourhood is required to generate a plane hypothesis. The planar facets enable line grouping and also the construction of parts of the wireframe which were missed due to the inevitable shortcomings of feature detection and matching. The method allows a piecewise planar model of a scene to be built completely automatically, with no user intervention at any stage, given only the images and camera projection matrices as input. The robustness and reliability of the method are illustrated on several examples, from both aerial and interior views.

/pdf/automatic-reconstruction-of-piecewise-planar-models-from-4nzy2v6d5p.pdf

Automatic reconstruction of piecewise planar models from multiple views

In this paper we describe an approach to recognizing poorly textured objects, that may contain holes and tubular parts, in cluttered scenes under arbitrary viewing conditions. To this end we develop a number of novel components. First, we introduce a new edge-based local feature detector that is invariant to similarity transformations. The features are localized on edges and a neighbourhood is estimated in a scale invariant manner. Second, the neighbourhood descriptor computed for foreground features is not affected by background clutter, even if the feature is on an object boundary. Third, the descriptor generalizes Lowe's SIFT method to edges. An object model is learnt from a single training image. The object is then recognized in new images in a series of steps which apply progressively tighter geometric restrictions. A final contribution of this work is to allow sufficient flexibility in the geometric representation that objects in the same visual class can be recognized. Results are demonstrated for various object classes including bikes and rackets.

/pdf/shape-recognition-with-edge-based-features-4s0uw7pr6a.pdf

Andrew Zisserman

Papers

Person spotting: video shot retrieval for face sets

“Who are you?” - Learning person specific classifiers from video

Scalable near identical image and shot detection

Automatic reconstruction of piecewise planar models from multiple views

Shape recognition with edge-based features